Transformers
Safetensors
nano_deep_reasoner_hypermini
causal-lm
decoder-only
reasoning
deep-reasoning
recurrent-transformer
adaptive-computation
chain-of-thought
adaptive-reasoning
Instructions to use 11-47/Nano.Deep.Reasoner.11m-HyperMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 11-47/Nano.Deep.Reasoner.11m-HyperMini with Transformers:
# Load model directly from transformers import HyperMiniReasoner model = HyperMiniReasoner.from_pretrained("11-47/Nano.Deep.Reasoner.11m-HyperMini", device_map="auto") - Notebooks
- Google Colab
- Kaggle
HyperMini Session 5 complete | 200,000 examples | loss=0.172932
Browse files- README.md +5 -5
- example_ledger.json +2 -2
- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pt +2 -2
- training_state.json +2 -2
README.md
CHANGED
|
@@ -87,16 +87,16 @@ before resume.
|
|
| 87 |
## Current state
|
| 88 |
|
| 89 |
Completed sessions:
|
| 90 |
-
|
| 91 |
|
| 92 |
Unique examples reserved/trained:
|
| 93 |
-
|
| 94 |
|
| 95 |
Unique completed examples:
|
| 96 |
-
|
| 97 |
|
| 98 |
Global optimizer steps:
|
| 99 |
-
|
| 100 |
|
| 101 |
Last session loss:
|
| 102 |
-
0.
|
|
|
|
| 87 |
## Current state
|
| 88 |
|
| 89 |
Completed sessions:
|
| 90 |
+
5
|
| 91 |
|
| 92 |
Unique examples reserved/trained:
|
| 93 |
+
0
|
| 94 |
|
| 95 |
Unique completed examples:
|
| 96 |
+
460,000
|
| 97 |
|
| 98 |
Global optimizer steps:
|
| 99 |
+
7,189
|
| 100 |
|
| 101 |
Last session loss:
|
| 102 |
+
0.17293200694084168
|
example_ledger.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1009cc4e9dc004353a9cceb878e79e6aedf1314942b21b26888a9dd78333507f
|
| 3 |
+
size 33121013
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 59742900
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:560d5b5f6e73cfee15dcd487b6fd1287b3cb8b608d50ed64ed884dd72d8282e5
|
| 3 |
size 59742900
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 88812619
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9418ab8a9e123ec3309edf740e0639c2614f2bea5b6d3c08e01a4fb06f2d226
|
| 3 |
size 88812619
|
rng_state.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:606300039d440abba1484df404c8ed0f7f6e6ff371525a8de8ada8ef2293fadd
|
| 3 |
+
size 10931
|
training_state.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad21b411be05db5ea183e4be9e6fdda0470fa5bc3a60482e695e89e13502502c
|
| 3 |
+
size 2407
|